Section: New Software and Platforms

4D-LFDE

Keywords: Light fields - Depth estimation

Functional Description: This code implements a learning based solution for disparity estimation for either densely or sparsely sampled light fields from 4 corner input views. The code contains two parts "DispEstim" and "DispPropa". The DispEstim module (implemented in tensorflow) takes the 4 corner views of a light field, and estimates the disparity information for these input view positions. The DispPropa module (implemented in Matlab) then generates one disparity map per target view position by propagating corner disparity maps and by applying an occlusion-aware soft 3D reconstruction method. The final output is a .mat file which contains disparity maps for every view positions of a light field.

• Participants: Xiaoran Jiang, Christine Guillemot and Jinglei Shi

• Contact: Xiaoran Jiang